<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>ᕕ( ᐛ )ᕗ SK&apos;s Blog</title><description>AI, coding &amp; games</description><link>https://sandykidyao.github.io/</link><item><title>关于在正式项目中使用 AI 编程工具提升效率</title><link>https://sandykidyao.github.io/blog/professional/2025-09-ai-coding-improved/</link><guid isPermaLink="true">https://sandykidyao.github.io/blog/professional/2025-09-ai-coding-improved/</guid><description>在企业级项目中使用 AI 编程工具的实践经验：工程维护、推荐工作流、模型策略与避坑指南。</description><pubDate>Tue, 09 Sep 2025 00:00:00 GMT</pubDate></item><item><title>当代码越来越便宜</title><link>https://sandykidyao.github.io/blog/professional/2026-02-when-code-goes-cheap/</link><guid isPermaLink="true">https://sandykidyao.github.io/blog/professional/2026-02-when-code-goes-cheap/</guid><description>AI 编程工具让代码越来越便宜，但写代码从来都不是软件工程最难的部分——这对开发者意味着什么。</description><pubDate>Tue, 24 Feb 2026 00:00:00 GMT</pubDate></item><item><title>AI Agent 与硬件</title><link>https://sandykidyao.github.io/blog/professional/2026-09-ai-and-hardware/</link><guid isPermaLink="true">https://sandykidyao.github.io/blog/professional/2026-09-ai-and-hardware/</guid><description>从 Anthropic 的模型硬件标准（MHS）出发，结合我做设备调度系统和让 LLM 实时控制设备的经历，聊聊 AI Agent 与硬件之间的关联与壁垒，以及把 LLM 变成程序本身一部分的设想。</description><pubDate>Thu, 03 Sep 2026 00:00:00 GMT</pubDate></item></channel></rss>